local/moss-image-base-dmd2

Local

MOSS-Image-Base is the OpenMOSS Team's Apache-2.0 1024 px text-to-image base model, with a Qwen3.5-9B text encoder and the FLUX.2 small-decoder VAE. This entry adds data-archetype's 8-step DMD2 LoRA, distilled on MOSS-Image-Base (a different LoRA from the DMD2 in the Kromoss repo), sampled with the fresh-noise sampler it was trained for.

Reproducibility

Download on motif64.sh ↗

You can download the exact source code and configuration that was used to generate these images, packaged as a capsule: MOSS-Image-Base + DMD2 8-step LoRA (diffusers) (NVIDIA GB10, 40 GB). Run it on your own machine with:

m64 m64_2804b385e240

Maker: OpenMOSS Team (LoRA: data-archetype)
Family: MOSS-Image
Model Size: 5B
medium
Cost: local run; no API price
not_applicable
Run Target: gx10/moss-image-base-dmd2
Effective Request: response_format: b64_json · size: 1024x1024 · num_inference_steps: 8 · guidance_scale: 1 · seed: 7
Sources: OpenMOSS-Team/MOSS-Image-Base model card data-archetype/moss_image_base_dmd2 (8-step DMD2 LoRA)MOSS-Image project page MOSS-Image technical report (arXiv 2610.23374)